Feature Diversity Learning with Sample Dropout for Unsupervised Domain Adaptive Person Re-identification

TL;DR

This paper introduces a novel feature diversity learning method with sample dropout to improve unsupervised domain adaptive person re-identification, effectively reducing noisy labels and enhancing generalization.

Contribution

It proposes a new Sample Dropout technique and a Feature Diversity Learning framework within mutual-teaching architecture for better feature generalization.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively reduces the impact of noisy pseudo labels.

Enhances feature representation generalization.

Abstract

Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable generalization ability during the whole training process. To solve these problems, this paper proposes a new approach to learn the feature representation with better generalization ability through limiting noisy pseudo labels. At first, we propose a Sample Dropout (SD) method to prevent the training of the model from falling into the vicious circle caused by samples that are frequently assigned with noisy pseudo labels. In addition, we put forward a brand-new method referred as to Feature Diversity Learning (FDL) under the classic mutual-teaching architecture, which can significantly improve the generalization ability of the feature representation on the target domain. Experimental results show that our proposed FDL-SD achieves the state-of-the-art performance on multiple benchmark datasets.